All challenges

Over the 48 hours, we will focus on three things.

First, building a lightweight fish-species recognition model, optimizing it to run with the lowest possible memory footprint on embedded ...

Evaluation of existing data augmentation strategies available Comparison of different AI approaches and models. Integration or experimentation with open-source tools such as VIAME, DIVE, LitDet, ...

An algorithm

An Algorithm as a backend and a dashboard running as a frontend

Over the 48-hour hackathon, we aim to build a working prototype of a digital system that makes sea turtle conservation faster and safer on a global scale. The heart of our project is an AI ...

Over the 48-hour hackathon, we aim to develop a working prototype of AquaTrace, an IoT-enabled mobile water quality monitoring system.

We will build a small-scale autonomous or semi-autonomous ...

The team will develop a functional prototype consisting of:

Interactive web-based dashboard
Marine debris hotspot prediction map
Environmental data integration engine
Coastal vulnerability ...

To develop a live AI verification platform — a web application where Chief Engineers upload or photograph a Bunker Delivery Note, and five specialized AI agents instantly analyze it for fraud, ...

We will build a complete water quality monitoring system from scratch.

Over 48 hours, the team will:
(1) Assemble and integrate sensors (pH, temperature, turbidity, etc.) with ESP32 ...

electronic IOT device and mobile + VR application

A classifier that can identify the species in an image, or produce a list of species sorted by likelihood of being a match, and report the lowest clade that contains the image can be classified as. ...